© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 83134
    Prev
    Next
    INDEX
    Explanations

    adverbs and expressions indicating degree or intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    超 / ちょっと / 绝

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .*")]
    -0.39
     zostać
    -0.37
     terlebih
    -0.34
    呤
    -0.33
     Übergang
    -0.33
     vivienda
    -0.32
     razões
    -0.32
     degrés
    -0.32
    likler
    -0.32
     plaats
    -0.32
    POSITIVE LOGITS
    超
    1.70
     超
    1.35
     siêu
    1.04
     super
    1.02
     Super
    0.93
     SUPER
    0.90
     súper
    0.90
    Super
    0.88
    super
    0.87
    超级
    0.83
    Activations Density 0.003%

    No Known Activations